Skip to main content
. 2021 Feb 6;11(7):jkab032. doi: 10.1093/g3journal/jkab032

Figure 1.

Figure 1

MLP for genomic prediction of a single trait with M SNP markers. The network has an input layer, two fully connected hidden layers, and an output layer. Each node’s input in the hidden layers is a transformation of the weighted sum of the output from the previous layer. The number of nodes in hidden layers decreases as the depth of the MLP increases, to facilitate the representation learning.